Merge tag 'block-5.13-2021-05-07' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - dasd spelling fixes (Bhaskar)

 - Limit bio max size on multi-page bvecs to the hardware limit, to
   avoid overly large bio's (and hence latencies). Originally queued for
   the merge window, but needed a fix and was dropped from the initial
   pull (Changheun)

 - NVMe pull request (Christoph):
      - reset the bdev to ns head when failover (Daniel Wagner)
      - remove unsupported command noise (Keith Busch)
      - misc passthrough improvements (Kanchan Joshi)
      - fix controller ioctl through ns_head (Minwoo Im)
      - fix controller timeouts during reset (Tao Chiu)

 - rnbd fixes/cleanups (Gioh, Md, Dima)

 - Fix iov_iter re-expansion (yangerkun)

* tag 'block-5.13-2021-05-07' of git://git.kernel.dk/linux-block:
  block: reexpand iov_iter after read/write
  nvmet: remove unsupported command noise
  nvme-multipath: reset bdev to ns head when failover
  nvme-pci: fix controller reset hang when racing with nvme_timeout
  nvme: move the fabrics queue ready check routines to core
  nvme: avoid memset for passthrough requests
  nvme: add nvme_get_ns helper
  nvme: fix controller ioctl through ns_head
  bio: limit bio max size
  RDMA/rtrs: fix uninitialized symbol 'cnt'
  s390: dasd: Mundane spelling fixes
  block/rnbd: Remove all likely and unlikely
  block/rnbd-clt: Check the return value of the function rtrs_clt_query
  block/rnbd: Fix style issues
  block/rnbd-clt: Change queue_depth type in rnbd_clt_session to size_t

block/bio.c

@@ -255,6 +255,13 @@ void bio_init(struct bio *bio, struct bio_vec *table,
 }
 EXPORT_SYMBOL(bio_init);
 
+unsigned int bio_max_size(struct bio *bio)
+{
+	struct block_device *bdev = bio->bi_bdev;
+
+	return bdev ? bdev->bd_disk->queue->limits.bio_max_bytes : UINT_MAX;
+}
+
 /**
  * bio_reset - reinitialize a bio
  * @bio:	bio to reset
@@ -866,7 +873,7 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page,
 		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
 		if (page_is_mergeable(bv, page, len, off, same_page)) {
-			if (bio->bi_iter.bi_size > UINT_MAX - len) {
+			if (bio->bi_iter.bi_size > bio_max_size(bio) - len) {
 				*same_page = false;
 				return false;
 			}
@@ -995,6 +1002,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
 	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
 	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
+	unsigned int bytes_left = bio_max_size(bio) - bio->bi_iter.bi_size;
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
 	bool same_page = false;
@@ -1010,7 +1018,8 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
 	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
 
-	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
+	size = iov_iter_get_pages(iter, pages, bytes_left, nr_pages,
+				  &offset);
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
 

block/blk-settings.c

@@ -32,6 +32,7 @@ EXPORT_SYMBOL_GPL(blk_queue_rq_timeout);
  */
 void blk_set_default_limits(struct queue_limits *lim)
 {
+	lim->bio_max_bytes = UINT_MAX;
 	lim->max_segments = BLK_MAX_SEGMENTS;
 	lim->max_discard_segments = 1;
 	lim->max_integrity_segments = 0;
@@ -140,6 +141,10 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 				 limits->logical_block_size >> SECTOR_SHIFT);
 	limits->max_sectors = max_sectors;
 
+	if (check_shl_overflow(max_sectors, SECTOR_SHIFT,
+				&limits->bio_max_bytes))
+		limits->bio_max_bytes = UINT_MAX;
+
 	q->backing_dev_info->io_pages = max_sectors >> (PAGE_SHIFT - 9);
 }
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);

drivers/block/rnbd/rnbd-clt.c

@@ -241,7 +241,7 @@ static bool rnbd_rerun_if_needed(struct rnbd_clt_session *sess)
 	     cpu_q = rnbd_get_cpu_qlist(sess, nxt_cpu(cpu_q->cpu))) {
 		if (!spin_trylock_irqsave(&cpu_q->requeue_lock, flags))
 			continue;
-		if (unlikely(!test_bit(cpu_q->cpu, sess->cpu_queues_bm)))
+		if (!test_bit(cpu_q->cpu, sess->cpu_queues_bm))
 			goto unlock;
 		q = list_first_entry_or_null(&cpu_q->requeue_list,
 					     typeof(*q), requeue_list);
@@ -320,7 +320,7 @@ static struct rtrs_permit *rnbd_get_permit(struct rnbd_clt_session *sess,
 	struct rtrs_permit *permit;
 
 	permit = rtrs_clt_get_permit(sess->rtrs, con_type, wait);
-	if (likely(permit))
+	if (permit)
 		/* We have a subtle rare case here, when all permits can be
 		 * consumed before busy counter increased.  This is safe,
 		 * because loser will get NULL as a permit, observe 0 busy
@@ -351,12 +351,11 @@ static struct rnbd_iu *rnbd_get_iu(struct rnbd_clt_session *sess,
 	struct rtrs_permit *permit;
 
 	iu = kzalloc(sizeof(*iu), GFP_KERNEL);
-	if (!iu) {
+	if (!iu)
 		return NULL;
-	}
 
 	permit = rnbd_get_permit(sess, con_type, wait);
-	if (unlikely(!permit)) {
+	if (!permit) {
 		kfree(iu);
 		return NULL;
 	}
@@ -692,7 +691,11 @@ static void remap_devs(struct rnbd_clt_session *sess)
 		return;
 	}
 
-	rtrs_clt_query(sess->rtrs, &attrs);
+	err = rtrs_clt_query(sess->rtrs, &attrs);
+	if (err) {
+		pr_err("rtrs_clt_query(\"%s\"): %d\n", sess->sessname, err);
+		return;
+	}
 	mutex_lock(&sess->lock);
 	sess->max_io_size = attrs.max_io_size;
 
@@ -805,7 +808,7 @@ static struct rnbd_clt_session *alloc_sess(const char *sessname)
 	mutex_init(&sess->lock);
 	INIT_LIST_HEAD(&sess->devs_list);
 	INIT_LIST_HEAD(&sess->list);
-	bitmap_zero(sess->cpu_queues_bm, NR_CPUS);
+	bitmap_zero(sess->cpu_queues_bm, num_possible_cpus());
 	init_waitqueue_head(&sess->rtrs_waitq);
 	refcount_set(&sess->refcount, 1);
 
@@ -1047,7 +1050,7 @@ static int rnbd_client_xfer_request(struct rnbd_clt_dev *dev,
 	};
 	err = rtrs_clt_request(rq_data_dir(rq), &req_ops, rtrs, permit,
 			       &vec, 1, size, iu->sgt.sgl, sg_cnt);
-	if (unlikely(err)) {
+	if (err) {
 		rnbd_clt_err_rl(dev, "RTRS failed to transfer IO, err: %d\n",
 				 err);
 		return err;
@@ -1078,7 +1081,7 @@ static bool rnbd_clt_dev_add_to_requeue(struct rnbd_clt_dev *dev,
 	cpu_q = get_cpu_ptr(sess->cpu_queues);
 	spin_lock_irqsave(&cpu_q->requeue_lock, flags);
 
-	if (likely(!test_and_set_bit_lock(0, &q->in_list))) {
+	if (!test_and_set_bit_lock(0, &q->in_list)) {
 		if (WARN_ON(!list_empty(&q->requeue_list)))
 			goto unlock;
 
@@ -1090,7 +1093,7 @@ static bool rnbd_clt_dev_add_to_requeue(struct rnbd_clt_dev *dev,
 			 */
 			smp_mb__before_atomic();
 		}
-		if (likely(atomic_read(&sess->busy))) {
+		if (atomic_read(&sess->busy)) {
 			list_add_tail(&q->requeue_list, &cpu_q->requeue_list);
 		} else {
 			/* Very unlikely, but possible: busy counter was
@@ -1118,7 +1121,7 @@ static void rnbd_clt_dev_kick_mq_queue(struct rnbd_clt_dev *dev,
 
 	if (delay != RNBD_DELAY_IFBUSY)
 		blk_mq_delay_run_hw_queue(hctx, delay);
-	else if (unlikely(!rnbd_clt_dev_add_to_requeue(dev, q)))
+	else if (!rnbd_clt_dev_add_to_requeue(dev, q))
 		/*
 		 * If session is not busy we have to restart
 		 * the queue ourselves.
@@ -1135,12 +1138,12 @@ static blk_status_t rnbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	int err;
 	blk_status_t ret = BLK_STS_IOERR;
 
-	if (unlikely(dev->dev_state != DEV_STATE_MAPPED))
+	if (dev->dev_state != DEV_STATE_MAPPED)
 		return BLK_STS_IOERR;
 
 	iu->permit = rnbd_get_permit(dev->sess, RTRS_IO_CON,
 				      RTRS_PERMIT_NOWAIT);
-	if (unlikely(!iu->permit)) {
+	if (!iu->permit) {
 		rnbd_clt_dev_kick_mq_queue(dev, hctx, RNBD_DELAY_IFBUSY);
 		return BLK_STS_RESOURCE;
 	}
@@ -1148,7 +1151,8 @@ static blk_status_t rnbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	iu->sgt.sgl = iu->first_sgl;
 	err = sg_alloc_table_chained(&iu->sgt,
 				     /* Even-if the request has no segment,
-				      * sglist must have one entry at least */
+				      * sglist must have one entry at least.
+				      */
 				     blk_rq_nr_phys_segments(rq) ? : 1,
 				     iu->sgt.sgl,
 				     RNBD_INLINE_SG_CNT);
@@ -1161,9 +1165,9 @@ static blk_status_t rnbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	blk_mq_start_request(rq);
 	err = rnbd_client_xfer_request(dev, rq, iu);
-	if (likely(err == 0))
+	if (err == 0)
 		return BLK_STS_OK;
-	if (unlikely(err == -EAGAIN || err == -ENOMEM)) {
+	if (err == -EAGAIN || err == -ENOMEM) {
 		rnbd_clt_dev_kick_mq_queue(dev, hctx, 10/*ms*/);
 		ret = BLK_STS_RESOURCE;
 	}
@@ -1294,7 +1298,11 @@ find_and_get_or_create_sess(const char *sessname,
 		err = PTR_ERR(sess->rtrs);
 		goto wake_up_and_put;
 	}
-	rtrs_clt_query(sess->rtrs, &attrs);
+
+	err = rtrs_clt_query(sess->rtrs, &attrs);
+	if (err)
+		goto close_rtrs;
+
 	sess->max_io_size = attrs.max_io_size;
 	sess->queue_depth = attrs.queue_depth;
 	sess->nr_poll_queues = nr_poll_queues;
@@ -1576,7 +1584,7 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname,
 	struct rnbd_clt_dev *dev;
 	int ret;
 
-	if (unlikely(exists_devpath(pathname, sessname)))
+	if (exists_devpath(pathname, sessname))
 		return ERR_PTR(-EEXIST);
 
 	sess = find_and_get_or_create_sess(sessname, paths, path_cnt, port_nr, nr_poll_queues);

drivers/block/rnbd/rnbd-clt.h

@@ -87,7 +87,7 @@ struct rnbd_clt_session {
 	DECLARE_BITMAP(cpu_queues_bm, NR_CPUS);
 	int	__percpu	*cpu_rr; /* per-cpu var for CPU round-robin */
 	atomic_t		busy;
-	int			queue_depth;
+	size_t			queue_depth;
 	u32			max_io_size;
 	struct blk_mq_tag_set	tag_set;
 	u32			nr_poll_queues;

drivers/block/rnbd/rnbd-srv.c

@@ -104,7 +104,7 @@ rnbd_get_sess_dev(int dev_id, struct rnbd_srv_session *srv_sess)
 
 	rcu_read_lock();
 	sess_dev = xa_load(&srv_sess->index_idr, dev_id);
-	if (likely(sess_dev))
+	if (sess_dev)
 		ret = kref_get_unless_zero(&sess_dev->kref);
 	rcu_read_unlock();
 

drivers/infiniband/ulp/rtrs/rtrs-clt.c

@@ -2976,7 +2976,8 @@ EXPORT_SYMBOL(rtrs_clt_request);
 
 int rtrs_clt_rdma_cq_direct(struct rtrs_clt *clt, unsigned int index)
 {
-	int cnt;
+	/* If no path, return -1 for block layer not to try again */
+	int cnt = -1;
 	struct rtrs_con *con;
 	struct rtrs_clt_sess *sess;
 	struct path_it it;

drivers/nvme/host/core.c

@@ -576,6 +576,11 @@ static void nvme_free_ns(struct kref *kref)
 	kfree(ns);
 }
 
+static inline bool nvme_get_ns(struct nvme_ns *ns)
+{
+	return kref_get_unless_zero(&ns->kref);
+}
+
 void nvme_put_ns(struct nvme_ns *ns)
 {
 	kref_put(&ns->kref, nvme_free_ns);
@@ -584,9 +589,6 @@ EXPORT_SYMBOL_NS_GPL(nvme_put_ns, NVME_TARGET_PASSTHRU);
 
 static inline void nvme_clear_nvme_request(struct request *req)
 {
-	struct nvme_command *cmd = nvme_req(req)->cmd;
-
-	memset(cmd, 0, sizeof(*cmd));
 	nvme_req(req)->retries = 0;
 	nvme_req(req)->flags = 0;
 	req->rq_flags |= RQF_DONTPREP;
@@ -637,6 +639,66 @@ static struct request *nvme_alloc_request_qid(struct request_queue *q,
 	return req;
 }
 
+/*
+ * For something we're not in a state to send to the device the default action
+ * is to busy it and retry it after the controller state is recovered.  However,
+ * if the controller is deleting or if anything is marked for failfast or
+ * nvme multipath it is immediately failed.
+ *
+ * Note: commands used to initialize the controller will be marked for failfast.
+ * Note: nvme cli/ioctl commands are marked for failfast.
+ */
+blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
+		struct request *rq)
+{
+	if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
+	    ctrl->state != NVME_CTRL_DEAD &&
+	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
+	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
+		return BLK_STS_RESOURCE;
+	return nvme_host_path_error(rq);
+}
+EXPORT_SYMBOL_GPL(nvme_fail_nonready_command);
+
+bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+		bool queue_live)
+{
+	struct nvme_request *req = nvme_req(rq);
+
+	/*
+	 * currently we have a problem sending passthru commands
+	 * on the admin_q if the controller is not LIVE because we can't
+	 * make sure that they are going out after the admin connect,
+	 * controller enable and/or other commands in the initialization
+	 * sequence. until the controller will be LIVE, fail with
+	 * BLK_STS_RESOURCE so that they will be rescheduled.
+	 */
+	if (rq->q == ctrl->admin_q && (req->flags & NVME_REQ_USERCMD))
+		return false;
+
+	if (ctrl->ops->flags & NVME_F_FABRICS) {
+		/*
+		 * Only allow commands on a live queue, except for the connect
+		 * command, which is require to set the queue live in the
+		 * appropinquate states.
+		 */
+		switch (ctrl->state) {
+		case NVME_CTRL_CONNECTING:
+			if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
+			    req->cmd->fabrics.fctype == nvme_fabrics_type_connect)
+				return true;
+			break;
+		default:
+			break;
+		case NVME_CTRL_DEAD:
+			return false;
+		}
+	}
+
+	return queue_live;
+}
+EXPORT_SYMBOL_GPL(__nvme_check_ready);
+
 static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
 {
 	struct nvme_command c;
@@ -898,8 +960,10 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req)
 	struct nvme_command *cmd = nvme_req(req)->cmd;
 	blk_status_t ret = BLK_STS_OK;
 
-	if (!(req->rq_flags & RQF_DONTPREP))
+	if (!(req->rq_flags & RQF_DONTPREP)) {
 		nvme_clear_nvme_request(req);
+		memset(cmd, 0, sizeof(*cmd));
+	}
 
 	switch (req_op(req)) {
 	case REQ_OP_DRV_IN:
@@ -1494,7 +1558,7 @@ static int nvme_ns_open(struct nvme_ns *ns)
 	/* should never be called due to GENHD_FL_HIDDEN */
 	if (WARN_ON_ONCE(nvme_ns_head_multipath(ns->head)))
 		goto fail;
-	if (!kref_get_unless_zero(&ns->kref))
+	if (!nvme_get_ns(ns))
 		goto fail;
 	if (!try_module_get(ns->ctrl->ops->module))
 		goto fail_put_ns;
@@ -1999,28 +2063,6 @@ static const struct block_device_operations nvme_bdev_ops = {
 	.pr_ops		= &nvme_pr_ops,
 };
 
-#ifdef CONFIG_NVME_MULTIPATH
-struct nvme_ctrl *nvme_find_get_live_ctrl(struct nvme_subsystem *subsys)
-{
-	struct nvme_ctrl *ctrl;
-	int ret;
-
-	ret = mutex_lock_killable(&nvme_subsystems_lock);
-	if (ret)
-		return ERR_PTR(ret);
-	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
-		if (ctrl->state == NVME_CTRL_LIVE)
-			goto found;
-	}
-	mutex_unlock(&nvme_subsystems_lock);
-	return ERR_PTR(-EWOULDBLOCK);
-found:
-	nvme_get_ctrl(ctrl);
-	mutex_unlock(&nvme_subsystems_lock);
-	return ctrl;
-}
-#endif /* CONFIG_NVME_MULTIPATH */
-
 static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
 {
 	unsigned long timeout =
@@ -3604,7 +3646,7 @@ struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list) {
 		if (ns->head->ns_id == nsid) {
-			if (!kref_get_unless_zero(&ns->kref))
+			if (!nvme_get_ns(ns))
 				continue;
 			ret = ns;
 			break;

drivers/nvme/host/fabrics.c

@@ -533,63 +533,6 @@ static struct nvmf_transport_ops *nvmf_lookup_transport(
 	return NULL;
 }
 
-/*
- * For something we're not in a state to send to the device the default action
- * is to busy it and retry it after the controller state is recovered.  However,
- * if the controller is deleting or if anything is marked for failfast or
- * nvme multipath it is immediately failed.
- *
- * Note: commands used to initialize the controller will be marked for failfast.
- * Note: nvme cli/ioctl commands are marked for failfast.
- */
-blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
-		struct request *rq)
-{
-	if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
-	    ctrl->state != NVME_CTRL_DEAD &&
-	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
-	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
-		return BLK_STS_RESOURCE;
-	return nvme_host_path_error(rq);
-}
-EXPORT_SYMBOL_GPL(nvmf_fail_nonready_command);
-
-bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live)
-{
-	struct nvme_request *req = nvme_req(rq);
-
-	/*
-	 * currently we have a problem sending passthru commands
-	 * on the admin_q if the controller is not LIVE because we can't
-	 * make sure that they are going out after the admin connect,
-	 * controller enable and/or other commands in the initialization
-	 * sequence. until the controller will be LIVE, fail with
-	 * BLK_STS_RESOURCE so that they will be rescheduled.
-	 */
-	if (rq->q == ctrl->admin_q && (req->flags & NVME_REQ_USERCMD))
-		return false;
-
-	/*
-	 * Only allow commands on a live queue, except for the connect command,
-	 * which is require to set the queue live in the appropinquate states.
-	 */
-	switch (ctrl->state) {
-	case NVME_CTRL_CONNECTING:
-		if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
-		    req->cmd->fabrics.fctype == nvme_fabrics_type_connect)
-			return true;
-		break;
-	default:
-		break;
-	case NVME_CTRL_DEAD:
-		return false;
-	}
-
-	return queue_live;
-}
-EXPORT_SYMBOL_GPL(__nvmf_check_ready);
-
 static const match_table_t opt_tokens = {
 	{ NVMF_OPT_TRANSPORT,		"transport=%s"		},
 	{ NVMF_OPT_TRADDR,		"traddr=%s"		},

drivers/nvme/host/fabrics.h

@@ -184,20 +184,7 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
 void nvmf_free_options(struct nvmf_ctrl_options *opts);
 int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
-blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
-		struct request *rq);
-bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live);
 bool nvmf_ip_options_match(struct nvme_ctrl *ctrl,
 		struct nvmf_ctrl_options *opts);
 
-static inline bool nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live)
-{
-	if (likely(ctrl->state == NVME_CTRL_LIVE ||
-		   ctrl->state == NVME_CTRL_DELETING))
-		return true;
-	return __nvmf_check_ready(ctrl, rq, queue_live);
-}
-
 #endif /* _NVME_FABRICS_H */

drivers/nvme/host/fc.c

@@ -2766,8 +2766,8 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx,
 	blk_status_t ret;
 
 	if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE ||
-	    !nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
-		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
+	    !nvme_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
+		return nvme_fail_nonready_command(&queue->ctrl->ctrl, rq);
 
 	ret = nvme_setup_cmd(ns, rq);
 	if (ret)

drivers/nvme/host/ioctl.c

@@ -370,41 +370,45 @@ long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 }
 
 #ifdef CONFIG_NVME_MULTIPATH
-static int nvme_ns_head_ctrl_ioctl(struct nvme_ns_head *head,
-		unsigned int cmd, void __user *argp)
+static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
+		void __user *argp, struct nvme_ns_head *head, int srcu_idx)
 {
-	struct nvme_ctrl *ctrl = nvme_find_get_live_ctrl(head->subsys);
+	struct nvme_ctrl *ctrl = ns->ctrl;
 	int ret;
 
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
-	ret = nvme_ctrl_ioctl(ctrl, cmd, argp);
-	nvme_put_ctrl(ctrl);
-	return ret;
-}
+	nvme_get_ctrl(ns->ctrl);
+	nvme_put_ns_from_disk(head, srcu_idx);
+	ret = nvme_ctrl_ioctl(ns->ctrl, cmd, argp);
 
-static int nvme_ns_head_ns_ioctl(struct nvme_ns_head *head,
-		unsigned int cmd, void __user *argp)
-{
-	int srcu_idx = srcu_read_lock(&head->srcu);
-	struct nvme_ns *ns = nvme_find_path(head);
-	int ret = -EWOULDBLOCK;
-
-	if (ns)
-		ret = nvme_ns_ioctl(ns, cmd, argp);
-	srcu_read_unlock(&head->srcu, srcu_idx);
+	nvme_put_ctrl(ctrl);
 	return ret;
 }
 
 int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode,
 		unsigned int cmd, unsigned long arg)
 {
-	struct nvme_ns_head *head = bdev->bd_disk->private_data;
+	struct nvme_ns_head *head = NULL;
 	void __user *argp = (void __user *)arg;
+	struct nvme_ns *ns;
+	int srcu_idx, ret;
 
+	ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
+	if (unlikely(!ns))
+		return -EWOULDBLOCK;
+
+	/*
+	 * Handle ioctls that apply to the controller instead of the namespace
+	 * seperately and drop the ns SRCU reference early.  This avoids a
+	 * deadlock when deleting namespaces using the passthrough interface.
+	 */
 	if (is_ctrl_ioctl(cmd))
-		return nvme_ns_head_ctrl_ioctl(head, cmd, argp);
-	return nvme_ns_head_ns_ioctl(head, cmd, argp);
+		ret = nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
+	else {
+		ret = nvme_ns_ioctl(ns, cmd, argp);
+		nvme_put_ns_from_disk(head, srcu_idx);
+	}
+
+	return ret;
 }
 
 long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd,
@@ -414,10 +418,23 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd,
 	struct nvme_ns_head *head =
 		container_of(cdev, struct nvme_ns_head, cdev);
 	void __user *argp = (void __user *)arg;
+	struct nvme_ns *ns;
+	int srcu_idx, ret;
+
+	srcu_idx = srcu_read_lock(&head->srcu);
+	ns = nvme_find_path(head);
+	if (!ns) {
+		srcu_read_unlock(&head->srcu, srcu_idx);
+		return -EWOULDBLOCK;
+	}
 
 	if (is_ctrl_ioctl(cmd))
-		return nvme_ns_head_ctrl_ioctl(head, cmd, argp);
-	return nvme_ns_head_ns_ioctl(head, cmd, argp);
+		return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
+
+	ret = nvme_ns_ioctl(ns, cmd, argp);
+	nvme_put_ns_from_disk(head, srcu_idx);
+
+	return ret;
 }
 #endif /* CONFIG_NVME_MULTIPATH */
 

drivers/nvme/host/multipath.c

@@ -70,6 +70,7 @@ void nvme_failover_req(struct request *req)
 	struct nvme_ns *ns = req->q->queuedata;
 	u16 status = nvme_req(req)->status & 0x7ff;
 	unsigned long flags;
+	struct bio *bio;
 
 	nvme_mpath_clear_current_path(ns);
 
@@ -84,6 +85,8 @@ void nvme_failover_req(struct request *req)
 	}
 
 	spin_lock_irqsave(&ns->head->requeue_lock, flags);
+	for (bio = req->bio; bio; bio = bio->bi_next)
+		bio_set_dev(bio, ns->head->disk->part0);
 	blk_steal_bios(&ns->head->requeue_list, req);
 	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
 

drivers/nvme/host/nvme.h

@@ -638,6 +638,21 @@ struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, blk_mq_req_flags_t flags);
 void nvme_cleanup_cmd(struct request *req);
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req);
+blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
+		struct request *req);
+bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+		bool queue_live);
+
+static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+		bool queue_live)
+{
+	if (likely(ctrl->state == NVME_CTRL_LIVE))
+		return true;
+	if (ctrl->ops->flags & NVME_F_FABRICS &&
+	    ctrl->state == NVME_CTRL_DELETING)
+		return true;
+	return __nvme_check_ready(ctrl, rq, queue_live);
+}
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buf, unsigned bufflen);
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
@@ -664,7 +679,6 @@ struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
 void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx);
 bool nvme_tryget_ns_head(struct nvme_ns_head *head);
 void nvme_put_ns_head(struct nvme_ns_head *head);
-struct nvme_ctrl *nvme_find_get_live_ctrl(struct nvme_subsystem *subsys);
 int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device,
 		const struct file_operations *fops, struct module *owner);
 void nvme_cdev_del(struct cdev *cdev, struct device *cdev_device);

drivers/nvme/host/pci.c

@@ -933,6 +933,9 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (unlikely(!test_bit(NVMEQ_ENABLED, &nvmeq->flags)))
 		return BLK_STS_IOERR;
 
+	if (!nvme_check_ready(&dev->ctrl, req, true))
+		return nvme_fail_nonready_command(&dev->ctrl, req);
+
 	ret = nvme_setup_cmd(ns, req);
 	if (ret)
 		return ret;

drivers/nvme/host/rdma.c

@@ -2050,8 +2050,8 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	WARN_ON_ONCE(rq->tag < 0);
 
-	if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
-		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
+	if (!nvme_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
+		return nvme_fail_nonready_command(&queue->ctrl->ctrl, rq);
 
 	dev = queue->device->dev;
 

drivers/nvme/host/tcp.c

@@ -2338,8 +2338,8 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx,
 	bool queue_ready = test_bit(NVME_TCP_Q_LIVE, &queue->flags);
 	blk_status_t ret;
 
-	if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
-		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
+	if (!nvme_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
+		return nvme_fail_nonready_command(&queue->ctrl->ctrl, rq);
 
 	ret = nvme_tcp_setup_cmd_pdu(ns, rq);
 	if (unlikely(ret))

drivers/nvme/target/admin-cmd.c

@@ -307,7 +307,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
 	case NVME_LOG_ANA:
 		return nvmet_execute_get_log_page_ana(req);
 	}
-	pr_err("unhandled lid %d on qid %d\n",
+	pr_debug("unhandled lid %d on qid %d\n",
 	       req->cmd->get_log_page.lid, req->sq->qid);
 	req->error_loc = offsetof(struct nvme_get_log_page_command, lid);
 	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
@@ -659,7 +659,7 @@ static void nvmet_execute_identify(struct nvmet_req *req)
 		return nvmet_execute_identify_desclist(req);
 	}
 
-	pr_err("unhandled identify cns %d on qid %d\n",
+	pr_debug("unhandled identify cns %d on qid %d\n",
 	       req->cmd->identify.cns, req->sq->qid);
 	req->error_loc = offsetof(struct nvme_identify, cns);
 	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
@@ -977,7 +977,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 		return 0;
 	}
 
-	pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
+	pr_debug("unhandled cmd %d on qid %d\n", cmd->common.opcode,
 	       req->sq->qid);
 	req->error_loc = offsetof(struct nvme_common_command, opcode);
 	return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;

drivers/nvme/target/loop.c

@@ -138,8 +138,8 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	bool queue_ready = test_bit(NVME_LOOP_Q_LIVE, &queue->flags);
 	blk_status_t ret;
 
-	if (!nvmf_check_ready(&queue->ctrl->ctrl, req, queue_ready))
-		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, req);
+	if (!nvme_check_ready(&queue->ctrl->ctrl, req, queue_ready))
+		return nvme_fail_nonready_command(&queue->ctrl->ctrl, req);
 
 	ret = nvme_setup_cmd(ns, req);
 	if (ret)

drivers/s390/block/dasd_eckd.h

@@ -52,7 +52,7 @@
 #define DASD_ECKD_CCW_RCD		 0xFA
 #define DASD_ECKD_CCW_DSO		 0xF7
 
-/* Define Subssystem Function / Orders */
+/* Define Subsystem Function / Orders */
 #define DSO_ORDER_RAS			 0x81
 
 /*
@@ -110,7 +110,7 @@
 #define DASD_ECKD_PG_GROUPED		 0x10
 
 /*
- * Size that is reportet for large volumes in the old 16-bit no_cyl field
+ * Size that is reported for large volumes in the old 16-bit no_cyl field
  */
 #define LV_COMPAT_CYL 0xFFFE
 
@@ -555,7 +555,7 @@ struct dasd_dso_ras_ext_range {
 } __packed;
 
 /*
- * Define Subsytem Operation - Release Allocated Space
+ * Define Subsystem Operation - Release Allocated Space
  */
 struct dasd_dso_ras_data {
 	__u8 order;
@@ -676,7 +676,7 @@ struct dasd_eckd_private {
 	struct dasd_ext_pool_sum eps;
 	u32 real_cyl;
 
-	/* alias managemnet */
+	/* alias management */
 	struct dasd_uid uid;
 	struct alias_pav_group *pavgroup;
 	struct alias_lcu *lcu;

fs/block_dev.c

@@ -1677,6 +1677,7 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *bd_inode = bdev_file_inode(file);
 	loff_t size = i_size_read(bd_inode);
 	struct blk_plug plug;
+	size_t shorted = 0;
 	ssize_t ret;
 
 	if (bdev_read_only(I_BDEV(bd_inode)))
@@ -1694,12 +1695,17 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT)
 		return -EOPNOTSUPP;
 
-	iov_iter_truncate(from, size - iocb->ki_pos);
+	size -= iocb->ki_pos;
+	if (iov_iter_count(from) > size) {
+		shorted = iov_iter_count(from) - size;
+		iov_iter_truncate(from, size);
+	}
 
 	blk_start_plug(&plug);
 	ret = __generic_file_write_iter(iocb, from);
 	if (ret > 0)
 		ret = generic_write_sync(iocb, ret);
+	iov_iter_reexpand(from, iov_iter_count(from) + shorted);
 	blk_finish_plug(&plug);
 	return ret;
 }
@@ -1711,13 +1717,21 @@ ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *bd_inode = bdev_file_inode(file);
 	loff_t size = i_size_read(bd_inode);
 	loff_t pos = iocb->ki_pos;
+	size_t shorted = 0;
+	ssize_t ret;
 
 	if (pos >= size)
 		return 0;
 
 	size -= pos;
+	if (iov_iter_count(to) > size) {
+		shorted = iov_iter_count(to) - size;
 		iov_iter_truncate(to, size);
-	return generic_file_read_iter(iocb, to);
+	}
+
+	ret = generic_file_read_iter(iocb, to);
+	iov_iter_reexpand(to, iov_iter_count(to) + shorted);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(blkdev_read_iter);
 

include/linux/bio.h

@@ -106,6 +106,8 @@ static inline void *bio_data(struct bio *bio)
 	return NULL;
 }
 
+extern unsigned int bio_max_size(struct bio *bio);
+
 /**
  * bio_full - check if the bio is full
  * @bio:	bio to check
@@ -119,7 +121,7 @@ static inline bool bio_full(struct bio *bio, unsigned len)
 	if (bio->bi_vcnt >= bio->bi_max_vecs)
 		return true;
 
-	if (bio->bi_iter.bi_size > UINT_MAX - len)
+	if (bio->bi_iter.bi_size > bio_max_size(bio) - len)
 		return true;
 
 	return false;

include/linux/blkdev.h

@@ -326,6 +326,8 @@ enum blk_bounce {
 };
 
 struct queue_limits {
+	unsigned int		bio_max_bytes;
+
 	enum blk_bounce		bounce;
 	unsigned long		seg_boundary_mask;
 	unsigned long		virt_boundary_mask;